1

I am trying to do html encoding for Chinese characters in my js file and it is returning some invalid characters.

My text :    奥妙 全自动洁彩深层洁净洗衣液3kg
My html encode:  kgoxAyM2tn
My htmldecoded term: �1#6

My code:

 // TODO get the ID of the select so that we can add this as a new dependency
                    var searchKeyword = $('#txtBox' + id).val();
                    var pId =  $('#SearchTerm_ > option:selected').attr("value");
                    var encodedSearchTerm = Encode(searchKeyword);
                    if (!(searchKeyword)) {
                        return false;
                    } else if (pId <= 0) {
                        return false;
                    }

     function Encode(urlFragment) {
     urlFragment = $.base64.encode(urlFragment);
     return urlFragment;
  };
2
  • 1
    Try using these functions here. They seem to work fine with your text. jsfiddle.net/gabrieleromanato/qAGHT Commented Apr 2, 2013 at 15:56
  • @better_use_mkstemp : This one worked. Please do an answer so that I can mark it. Thanks Commented Apr 2, 2013 at 16:08

1 Answer 1

3

Posting as an answer:

This jfiddle to do the encoding will get you where you need:

http://jsfiddle.net/gabrieleromanato/qAGHT/

var Base64 = {


_keyStr: "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=",


encode: function(input) {
    var output = "";
    var chr1, chr2, chr3, enc1, enc2, enc3, enc4;
    var i = 0;

    input = Base64._utf8_encode(input);

    while (i < input.length) {

        chr1 = input.charCodeAt(i++);
        chr2 = input.charCodeAt(i++);
        chr3 = input.charCodeAt(i++);

        enc1 = chr1 >> 2;
        enc2 = ((chr1 & 3) << 4) | (chr2 >> 4);
        enc3 = ((chr2 & 15) << 2) | (chr3 >> 6);
        enc4 = chr3 & 63;

        if (isNaN(chr2)) {
            enc3 = enc4 = 64;
        } else if (isNaN(chr3)) {
            enc4 = 64;
        }

        output = output + this._keyStr.charAt(enc1) + this._keyStr.charAt(enc2) + this._keyStr.charAt(enc3) + this._keyStr.charAt(enc4);

    }

    return output;
},


decode: function(input) {
    var output = "";
    var chr1, chr2, chr3;
    var enc1, enc2, enc3, enc4;
    var i = 0;

    input = input.replace(/[^A-Za-z0-9\+\/\=]/g, "");

    while (i < input.length) {

        enc1 = this._keyStr.indexOf(input.charAt(i++));
        enc2 = this._keyStr.indexOf(input.charAt(i++));
        enc3 = this._keyStr.indexOf(input.charAt(i++));
        enc4 = this._keyStr.indexOf(input.charAt(i++));

        chr1 = (enc1 << 2) | (enc2 >> 4);
        chr2 = ((enc2 & 15) << 4) | (enc3 >> 2);
        chr3 = ((enc3 & 3) << 6) | enc4;

        output = output + String.fromCharCode(chr1);

        if (enc3 != 64) {
            output = output + String.fromCharCode(chr2);
        }
        if (enc4 != 64) {
            output = output + String.fromCharCode(chr3);
        }

    }

    output = Base64._utf8_decode(output);

    return output;

},

_utf8_encode: function(string) {
    string = string.replace(/\r\n/g, "\n");
    var utftext = "";

    for (var n = 0; n < string.length; n++) {

        var c = string.charCodeAt(n);

        if (c < 128) {
            utftext += String.fromCharCode(c);
        }
        else if ((c > 127) && (c < 2048)) {
            utftext += String.fromCharCode((c >> 6) | 192);
            utftext += String.fromCharCode((c & 63) | 128);
        }
        else {
            utftext += String.fromCharCode((c >> 12) | 224);
            utftext += String.fromCharCode(((c >> 6) & 63) | 128);
            utftext += String.fromCharCode((c & 63) | 128);
        }

    }

    return utftext;
},

_utf8_decode: function(utftext) {
    var string = "";
    var i = 0;
    var c = c1 = c2 = 0;

    while (i < utftext.length) {

        c = utftext.charCodeAt(i);

        if (c < 128) {
            string += String.fromCharCode(c);
            i++;
        }
        else if ((c > 191) && (c < 224)) {
            c2 = utftext.charCodeAt(i + 1);
            string += String.fromCharCode(((c & 31) << 6) | (c2 & 63));
            i += 2;
        }
        else {
            c2 = utftext.charCodeAt(i + 1);
            c3 = utftext.charCodeAt(i + 2);
            string += String.fromCharCode(((c & 15) << 12) | ((c2 & 63) << 6) | (c3 & 63));
            i += 3;
        }

    }

    return string;
}

}



var encode = document.getElementById('encode'),
decode = document.getElementById('decode'),
output = document.getElementById('output'),
input = document.getElementById('input');


encode.onclick = function() {
output.innerHTML = Base64.encode(input.value);
}

decode.onclick = function() {
var $str = output.innerHTML;
output.innerHTML = Base64.decode($str);
}    

The JavaScript can be used to encode / decode data with MIME base64 and is fully compatible with UTF-8 encoding.

Sign up to request clarification or add additional context in comments.

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.